mlsanityData to 7 Oct 2026

Critical Sampling for Robust Evolution Operator Learning of Unknown Dynamical Systems

arXiv 2304.07485 ↗First posted 15 Apr 2023cs.LG cs.AI cs.NAcited by 0

Not on the map. Why?

Abstract (arXiv)

Given an unknown dynamical system, what is the minimum number of samples needed for effective learning of its governing laws and accurate prediction of its future evolution behavior, and how to select these critical samples? In this work, we propose to explore this problem based on a design approach. Starting from a small initial set of samples, we adaptively discover critical samples to achieve increasingly accurate learning of the system evolution. One central challenge here is that we do not know the network modeling error since the ground-truth system state is unknown, which is however needed for critical sampling. To address this challenge, we introduce a multi-step reciprocal prediction network where forward and backward evolution networks are designed to learn the temporal evolution behavior in the forward and backward time directions, respectively. Very interestingly, we find that the desired network modeling error is highly correlated with the multi-step reciprocal prediction error, which can be directly computed from the current system state. This allows us to perform a dynamic selection of critical samples from regions with high network modeling errors for dynamical systems. Additionally, a joint spatial-temporal evolution network is introduced which incorporates spatial dynamics modeling into the temporal evolution prediction for robust learning of the system evolution operator with few samples. Our extensive experimental results demonstrate that our proposed method is able to dramatically reduce the number of samples needed for effective learning and accurate prediction of evolution behaviors of unknown dynamical systems by up to hundreds of times.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 31 of its 61 references that are in the map. First posted on arXiv 15 Apr 2023.

Builds on

31 of 61 references.

References · 31

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2018Neural Ordinary Differential Equationscited by 3,733
  3. 2020Fourier Neural Operator for Parametric Partial Differential Equationscited by 2,806
  4. 2021Physics-Informed Neural Operator for Learning Partial Differential Equationscited by 516
  5. 2017PDE-Net: Learning PDEs from Datacited by 304
  6. 2018Deep Hidden Physics Models: Deep Learning of Nonlinear Partial Differential Equationscited by 233
  7. 2022A comprehensive study of non-adaptive and residual-based adaptive sampling for physics-informed neural networkscited by 233
  8. 2018PDE-Net 2.0: Learning PDEs from Data with A Numeric-Symbolic Hybrid Deep Networkcited by 208
  9. 2018Data-Driven Forecasting of High-Dimensional Chaotic Systems with Long Short-Term Memory Networkscited by 155
  10. 2017Machine Learning of Linear Differential Equations using Gaussian Processescited by 139
  11. 2016Composing graphical models with neural networks for structured representations and fast inferencecited by 113
  12. 2019Lift & Learn: Physics-informed machine learning for large-scale nonlinear dynamical systemscited by 96
19 more
  1. 2018Data Driven Governing Equations Approximation Using Deep Neural Networkscited by 94
  2. 2020Active Learning for Nonlinear System Identification with Guaranteescited by 78
  3. 2020Adaptive Checkpoint Adjoint Method for Gradient Estimation in Neural ODEcited by 76
  4. 2022Failure-informed adaptive sampling for PINNscited by 64
  5. 2017Extracting Sparse High-Dimensional Dynamics from Limited Datacited by 50
  6. 2019Data-Driven Deep Learning of Partial Differential Equations in Modal Spacecited by 46
  7. 2020DLGA-PDE: Discovery of PDEs with incomplete candidate library via combination of deep learning and genetic algorithmcited by 45
  8. 2021MALI: A memory efficient and reverse accurate integrator for Neural ODEscited by 42
  9. 2016Linear dynamical neural population models through nonlinear embeddingscited by 36
  10. 2022Thermodynamics-informed graph neural networkscited by 31
  11. 2021Deep Neural Network Modeling of Unknown Partial Differential Equations in Nodal Spacecited by 25
  12. 2018Numerical Aspects for Approximating Governing Equations Using Datacited by 21
  13. 2021Robust discovery of partial differential equations in complex situationscited by 21
  14. 2020Learning reduced systems via deep neural networks with memorycited by 20
  15. 2020Deep-learning of Parametric Partial Differential Equations from Sparse and Noisy Datacited by 19
  16. 2019Structure-preserving Method for Reconstructing Unknown Hamiltonian Systems from Trajectory Datacited by 18
  17. 2019Discovery of Dynamics Using Linear Multistep Methodscited by 16
  18. 2020On generalized residue network for deep learning of unknown dynamical systemscited by 16
  19. 2021Physics-Coupled Spatio-Temporal Active Learning for Dynamical Systemscited by 2

Built on by

Not cited yet.